A scheduled macroeconomic release. Prints that miss their forecast tend to move related markets sharply in the minutes around the release, which is why a validation run that straddles the window is hard to compare with a backtest that never saw it.
| Date (UTC) | Actual | Forecast | Previous | Surprise |
|---|---|---|---|---|
| 17 Aug 2026, 07:00 | -6.7% | -6.2% | -5.7% | -0.5 |
| 15 Jul 2026, 02:00 | -5.7% | -4.9% | -4.1% | -0.8 |
| 16 Jun 2026, 02:00 | -4.1% | -2% | -1.6% | -2.1 |
| 18 May 2026, 02:00 | -1.6% | 1.6% | 1.7% | -3.2 |
| 16 Apr 2026, 02:00 | 1.7% | 1.9% | 1.8% | -0.2 |
| 16 Mar 2026, 02:00 | 1.8% | -0.4% | -3.8% | +2.2 |
| 19 Jan 2026, 02:00 | -3.8% | -3% | -2.6% | -0.8 |
| 15 Dec 2025, 02:00 | -2.6% | -2.3% | -1.7% | -0.3 |
| 14 Nov 2025, 02:00 | -1.7% | -0.8% | -0.5% | -0.9 |
| 20 Oct 2025, 02:00 | -0.5% | 0.2% | 0.5% | -0.7 |
| 15 Sep 2025, 02:00 | 0.5% | 1.4% | 1.6% | -0.9 |
| 15 Aug 2025, 02:00 | 1.6% | 2.7% | 2.8% | -1.1 |
Surprise is actual minus forecast, in the indicator's own units. It is what happened, not a prediction.
Spreads widen and fills slip in the minutes around a scheduled release, which distorts a validation run's entry prices. Treat forward results that straddle this window with care — they are not comparable to a backtest that never saw it.
High-impact releases are posted to the channel 15 minutes ahead, and again with the actual figure once it prints.